Vector store support for Cassandra #6426
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@hemidactylus is attempting to deploy a commit to the LangChain Team on Vercel. A member of the Team first needs to authorize it. |
rlancemartin
force-pushed
the
SL-cassandra-vector-store
branch
4 times, most recently
from
155acaa to
95ce962
Compare
rlancemartin
force-pushed
the
SL-cassandra-vector-store
branch
from
95ce962 to
b0d9b7e
Compare
rlancemartin
approved these changes
Jun 20, 2023
bdonkey
added a commit
to bdonkey/langchain
that referenced
this pull request
Jun 20, 2023
* master: (158 commits) Fix link (langchain-ai#6501) docs/fix links (langchain-ai#6498) Update notebook for MD header splitter and create new cookbook (langchain-ai#6399) Vector store support for Cassandra (langchain-ai#6426) improve documentation on base chain (langchain-ai#6468) fix: change ddg to DDGS (langchain-ai#6480) release 207 (langchain-ai#6488) Add Alibaba Cloud OpenSearch as a new vector store (langchain-ai#6154) fix openai qa chain (langchain-ai#6487) add FunctionMessage support to `_convert_dict_to_message()` in OpenAI chat model (langchain-ai#6382) bump version to 206 (langchain-ai#6465) fix neo4j schema query (langchain-ai#6381) Update serpapi.py Support baidu list type answer_box (langchain-ai#6386) fix: llm caching for replicate (langchain-ai#6396) feat: use latest duckduckgo_search API to call (langchain-ai#6409) Harrison/unstructured page number (langchain-ai#6464) Improve error message (langchain-ai#6275) Fix the issue where ANTHROPIC_API_URL set in environment is not takin… (langchain-ai#6400) Fix broken links in autonomous agents docs (langchain-ai#6398) Update SinglStoreDB vectorstore (langchain-ai#6423) ...
rlancemartin
pushed a commit
that referenced
this pull request
Jun 29, 2023
### Overview This PR aims at building on #4378, expanding the capabilities and building on top of the `cassIO` library to interface with the database (as opposed to using the core drivers directly). Usage of `cassIO` (a library abstracting Cassandra access for ML/GenAI-specific purposes) is already established since #6426 was merged, so no new dependencies are introduced. In the same spirit, we try to uniform the interface for using Cassandra instances throughout LangChain: all our appreciation of the work by @jj701 notwithstanding, who paved the way for this incremental work (thank you!), we identified a few reasons for changing the way a `CassandraChatMessageHistory` is instantiated. Advocating a syntax change is something we don't take lighthearted way, so we add some explanations about this below. Additionally, this PR expands on integration testing, enables use of Cassandra's native Time-to-Live (TTL) features and improves the phrasing around the notebook example and the short "integrations" documentation paragraph. We would kindly request @hwchase to review (since this is an elaboration and proposed improvement of #4378 who had the same reviewer). ### About the __init__ breaking changes There are [many](https://docs.datastax.com/en/developer/python-driver/3.28/api/cassandra/cluster/) options when creating the `Cluster` object, and new ones might be added at any time. Choosing some of them and exposing them as `__init__` parameters `CassandraChatMessageHistory` will prove to be insufficient for at least some users. On the other hand, working through `kwargs` or adding a long, long list of arguments to `__init__` is not a desirable option either. For this reason, (as done in #6426), we propose that whoever instantiates the Chat Message History class provide a Cassandra `Session` object, ready to use. This also enables easier injection of mocks and usage of Cassandra-compatible connections (such as those to the cloud database DataStax Astra DB, obtained with a different set of init parameters than `contact_points` and `port`). We feel that a breaking change might still be acceptable since LangChain is at `0.*`. However, while maintaining that the approach we propose will be more flexible in the future, room could be made for a "compatibility layer" that respects the current init method. Honestly, we would to that only if there are strong reasons for it, as that would entail an additional maintenance burden. ### Other changes We propose to remove the keyspace creation from the class code for two reasons: first, production Cassandra instances often employ RBAC so that the database user reading/writing from tables does not necessarily (and generally shouldn't) have permission to create keyspaces, and second that programmatic keyspace creation is not a best practice (it should be done more or less manually, with extra care about schema mismatched among nodes, etc). Removing this (usually unnecessary) operation from the `__init__` path would also improve initialization performance (shorter time). We suggest, likewise, to remove the `__del__` method (which would close the database connection), for the following reason: it is the recommended best practice to create a single Cassandra `Session` object throughout an application (it is a resource-heavy object capable to handle concurrency internally), so in case Cassandra is used in other ways by the app there is the risk of truncating the connection for all usages when the history instance is destroyed. Moreover, the `Session` object, in typical applications, is best left to garbage-collect itself automatically. As mentioned above, we defer the actual database I/O to the `cassIO` library, which is designed to encode practices optimized for LLM applications (among other) without the need to expose LangChain developers to the internals of CQL (Cassandra Query Language). CassIO is already employed by the LangChain's Vector Store support for Cassandra. We added a few more connection options in the companion notebook example (most notably, Astra DB) to encourage usage by anyone who cannot run their own Cassandra cluster. We surface the `ttl_seconds` option for automatic handling of an expiration time to chat history messages, a likely useful feature given that very old messages generally may lose their importance. We elaborated a bit more on the integration testing (Time-to-live, separation of "session ids", ...). ### Remarks from linter & co. We reinstated `cassio` as a dependency both in the "optional" group and in the "integration testing" group of `pyproject.toml`. This might not be the right thing do to, in which case the author of this PR offer his apologies (lack of confidence with Poetry - happy to be pointed in the right direction, though!). During linter tests, we were hit by some errors which appear unrelated to the code in the PR. We left them here and report on them here for awareness: ``` langchain/vectorstores/mongodb_atlas.py:137: error: Argument 1 to "insert_many" of "Collection" has incompatible type "List[Dict[str, Sequence[object]]]"; expected "Iterable[Union[MongoDBDocumentType, RawBSONDocument]]" [arg-type] langchain/vectorstores/mongodb_atlas.py:186: error: Argument 1 to "aggregate" of "Collection" has incompatible type "List[object]"; expected "Sequence[Mapping[str, Any]]" [arg-type] langchain/vectorstores/qdrant.py:16: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:19: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:20: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:22: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:23: error: Name "grpc" is not defined [name-defined] ``` In the same spirit, we observe that to even get `import langchain` run, it seems that a `pip install bs4` is missing from the minimal package installation path. Thank you!
1 task
vowelparrot
pushed a commit
that referenced
this pull request
Jul 4, 2023
### Overview This PR aims at building on #4378, expanding the capabilities and building on top of the `cassIO` library to interface with the database (as opposed to using the core drivers directly). Usage of `cassIO` (a library abstracting Cassandra access for ML/GenAI-specific purposes) is already established since #6426 was merged, so no new dependencies are introduced. In the same spirit, we try to uniform the interface for using Cassandra instances throughout LangChain: all our appreciation of the work by @jj701 notwithstanding, who paved the way for this incremental work (thank you!), we identified a few reasons for changing the way a `CassandraChatMessageHistory` is instantiated. Advocating a syntax change is something we don't take lighthearted way, so we add some explanations about this below. Additionally, this PR expands on integration testing, enables use of Cassandra's native Time-to-Live (TTL) features and improves the phrasing around the notebook example and the short "integrations" documentation paragraph. We would kindly request @hwchase to review (since this is an elaboration and proposed improvement of #4378 who had the same reviewer). ### About the __init__ breaking changes There are [many](https://docs.datastax.com/en/developer/python-driver/3.28/api/cassandra/cluster/) options when creating the `Cluster` object, and new ones might be added at any time. Choosing some of them and exposing them as `__init__` parameters `CassandraChatMessageHistory` will prove to be insufficient for at least some users. On the other hand, working through `kwargs` or adding a long, long list of arguments to `__init__` is not a desirable option either. For this reason, (as done in #6426), we propose that whoever instantiates the Chat Message History class provide a Cassandra `Session` object, ready to use. This also enables easier injection of mocks and usage of Cassandra-compatible connections (such as those to the cloud database DataStax Astra DB, obtained with a different set of init parameters than `contact_points` and `port`). We feel that a breaking change might still be acceptable since LangChain is at `0.*`. However, while maintaining that the approach we propose will be more flexible in the future, room could be made for a "compatibility layer" that respects the current init method. Honestly, we would to that only if there are strong reasons for it, as that would entail an additional maintenance burden. ### Other changes We propose to remove the keyspace creation from the class code for two reasons: first, production Cassandra instances often employ RBAC so that the database user reading/writing from tables does not necessarily (and generally shouldn't) have permission to create keyspaces, and second that programmatic keyspace creation is not a best practice (it should be done more or less manually, with extra care about schema mismatched among nodes, etc). Removing this (usually unnecessary) operation from the `__init__` path would also improve initialization performance (shorter time). We suggest, likewise, to remove the `__del__` method (which would close the database connection), for the following reason: it is the recommended best practice to create a single Cassandra `Session` object throughout an application (it is a resource-heavy object capable to handle concurrency internally), so in case Cassandra is used in other ways by the app there is the risk of truncating the connection for all usages when the history instance is destroyed. Moreover, the `Session` object, in typical applications, is best left to garbage-collect itself automatically. As mentioned above, we defer the actual database I/O to the `cassIO` library, which is designed to encode practices optimized for LLM applications (among other) without the need to expose LangChain developers to the internals of CQL (Cassandra Query Language). CassIO is already employed by the LangChain's Vector Store support for Cassandra. We added a few more connection options in the companion notebook example (most notably, Astra DB) to encourage usage by anyone who cannot run their own Cassandra cluster. We surface the `ttl_seconds` option for automatic handling of an expiration time to chat history messages, a likely useful feature given that very old messages generally may lose their importance. We elaborated a bit more on the integration testing (Time-to-live, separation of "session ids", ...). ### Remarks from linter & co. We reinstated `cassio` as a dependency both in the "optional" group and in the "integration testing" group of `pyproject.toml`. This might not be the right thing do to, in which case the author of this PR offer his apologies (lack of confidence with Poetry - happy to be pointed in the right direction, though!). During linter tests, we were hit by some errors which appear unrelated to the code in the PR. We left them here and report on them here for awareness: ``` langchain/vectorstores/mongodb_atlas.py:137: error: Argument 1 to "insert_many" of "Collection" has incompatible type "List[Dict[str, Sequence[object]]]"; expected "Iterable[Union[MongoDBDocumentType, RawBSONDocument]]" [arg-type] langchain/vectorstores/mongodb_atlas.py:186: error: Argument 1 to "aggregate" of "Collection" has incompatible type "List[object]"; expected "Sequence[Mapping[str, Any]]" [arg-type] langchain/vectorstores/qdrant.py:16: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:19: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:20: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:22: error: Name "grpc" is not defined [name-defined] langchain/vectorstores/qdrant.py:23: error: Name "grpc" is not defined [name-defined] ``` In the same spirit, we observe that to even get `import langchain` run, it seems that a `pip install bs4` is missing from the minimal package installation path. Thank you!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This addresses #6291 adding support for using Cassandra (and compatible databases, such as DataStax Astra DB) as a Vector Store.
A new class
Cassandrais introduced, which complies with the contract and interface for a vector store, along with the corresponding integration test, a sample notebook and modified dependency toml.Dependencies: the implementation relies on the library
cassio, which simplifies interacting with Cassandra for ML- and LLM-oriented workloads. CassIO, in turn, uses thecassandra-driverlow-lever drivers to communicate with the database. The former is added as optional dependency (+ inextended_testing), the latter was already in the project.Integration testing relies on a locally-running instance of Cassandra. Here a detailed description can be found on how to compile and run it (at the time of writing the feature has not made it yet to a release).
During development of the integration tests, I added a new "fake embedding" class for what I consider a more controlled way of testing the MMR search method. Likewise, I had to amend what looked like a glitch in the behaviour of
ConsistentFakeEmbeddingswhereby anembed_querycall would have bypassed storage of the requested text in the class cache for use in later repeated invocations.@dev2049 might be the right person to tag here for a review. Thank you!